Report alleles (#4)

* Add v0.2 of pipeline * Use new version of screen_abricate_report and write alleles to line list * Add updated images and prepare for v0.2.0 release * Write CHANGELOG.md
Public-Health-Bioinformatics · Jan 3, 2020 · 7fa8b54 · 7fa8b54
1 parent de64703
commit 7fa8b54
Show file tree

Hide file tree

Showing 15 changed files with 125 additions and 98 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -1,3 +1,20 @@
+# 0.2.0
+
+- For each gene in the 'gene screening file', both the 'detection status' (True/False) and the detected allele
+  are written to the IRIDA line-list. Alleles are also reported in the 'gene_detection_status.tsv' output file.
+- Limited pipeline parameters to simplify and standardize operation
+  - Resistance Gene Database is fixed on CARD database.
+  - Cannot disable post-assembly correction or read trimming.
+  - Cannot change contig name format
+  - Cannot provide 'extra spades options' to shovill assembler
+- Added thresholds for resistance gene %Coverage and %Identity during secondary screening phase
+- The gene screening file used for the analysis is included in the pipeline output
+
+# 0.1.1
+
+- Fixed [issue](https://github.com/Public-Health-Bioinformatics/irida-plugin-resistance-screen/issues/1) where sequence data was not being transferred to galaxy
+
 # 0.1.0
 
-* Initial release of example plugin.
+- Initial release of example plugin.
+
diff --git a/README.md b/README.md
@@ -36,7 +36,7 @@ managers within your Galaxy instance. These can be found at:
 | shovill                            | `1.0.4`         | `iuc`                          | 3 (2018-11-13)    | [shovill-3:865119fcb694](https://toolshed.g2.bx.psu.edu/view/iuc/shovill/865119fcb694)                                                            |
 | quast                              | `5.0.2`         | `iuc`                          | 5 (2018-12-04)    | [quast-5:81df4950d65b](https://toolshed.g2.bx.psu.edu/view/iuc/quast/81df4950d65b)                                                                |
 | abricate                           | `0.9.8`         | `iuc`                          | 7 (2019-10-29)    | [abricate-7:4efdca267d51](https://toolshed.g2.bx.psu.edu/view/iuc/abricate/4efdca267d51)                                                          |
-| screen_abricate_report             | `0.1.0`         | `public-health-bioinformatics` | 0 (2019-10-31)    | [screen_abricate_report-0:b2d56a44a872](https://toolshed.g2.bx.psu.edu/view/public-health-bioinformatics/screen_abricate_report/b2d56a44a872)     |
+| screen_abricate_report             | `0.4.0`         | `public-health-bioinformatics` | 4 (2020-01-02)    | [screen_abricate_report-4:22247b1a59d5](https://toolshed.g2.bx.psu.edu/view/public-health-bioinformatics/screen_abricate_report/22247b1a59d5)     |
 | data_manager_manual                | `0.0.2`         | `iuc`                          | 5 (2019-10-21)    | [data_manager_manual-5:744f607fac50](https://toolshed.g2.bx.psu.edu/view/iuc/data_manager_manual/744f607fac50)                                    |
 
 ## Installing to IRIDA
@@ -49,13 +49,13 @@ Please download the provided `irida-plugin-resistance-screen-[version].jar` from
 ## Setting up your abricate report screening file(s)
 
 Abricate report screening files have a simple tabular format, and can be created with Excel, another spreadsheet application,
-or a plaintext editor. They consist of two columns, with headings `gene_name` and `regex`. All fields should be tab-delimited.
+or a plaintext editor. They consist of two columns, with headings `gene_name` and `regex`. All fields must be tab-delimited.
 
 ```
 gene_name    regex
-KPC          KPC
-OXA-48       OXA\-48
-NDM          NDM
+KPC          ^KPC-\d+$
+OXA          ^OXA-\d+$
+NDM          ^NDM-\d+$
 ```
 
 ## Preparing the 'abricate_report_screening_files' Tool Data Table in Galaxy
@@ -86,9 +86,10 @@ report, and a screened `abricate` report that includes only your genes of intere
 And, you should be able to save and view these results in the IRIDA metadata table. The following fields are written to
 the IRIDA 'Line List':
 
-| Field Name                                 | Description                                               |
-|--------------------------------------------|-----------------------------------------------------------|
-| resistance-screen/<GENE_NAME>/detected     | Whether or not `GENE_NAME` was detected (True/False)      |
+| Field Name                                 | Description                                                                                                |
+|--------------------------------------------|------------------------------------------------------------------------------------------------------------|
+| resistance-screen/<GENE_NAME>/detected     | Whether or not `GENE_NAME` was detected (True/False)                                                       |
+| resistance-screen/<GENE_NAME>/alleles      | Any allele(s) detected for `GENE_NAME`. If multiple alleles detected, commma-delimited (eg: `KPC-2,KPC-3`) |
 
 **Note**: If your abricate report screening file contains many genes, this will result in many columns 
 

diff --git a/doc/images/pipeline-parameters.png b/doc/images/pipeline-parameters.png
diff --git a/doc/images/plugin-metadata.png b/doc/images/plugin-metadata.png
diff --git a/doc/images/plugin-results-1.png b/doc/images/plugin-results-1.png
diff --git a/doc/images/plugin-results-2.png b/doc/images/plugin-results-2.png
diff --git a/doc/images/plugin-results-3.png b/doc/images/plugin-results-3.png
diff --git a/pom.xml b/pom.xml
@@ -6,14 +6,14 @@
 
 	<groupId>org.publichealthbioinformatics</groupId>
 	<artifactId>irida-plugin-resistance-screen</artifactId>
-	<version>0.2.0-SNAPSHOT</version>
+	<version>0.2.0</version>
 
 	<!-- Please fill out these properties with information about your particular plugin -->
 	<properties>
 		<!-- Information used to define properties about a plugin. Please see the PF4J docs for more details https://pf4j.org/doc/getting-started.html -->
 		<plugin.id>resistance-screen</plugin.id>
 		<plugin.class>org.publichealthbioinformatics.irida.plugin.resistancescreen.ResistanceScreenPlugin</plugin.class>
-		<plugin.version>0.2.0-SNAPSHOT</plugin.version>
+		<plugin.version>0.2.0</plugin.version>
 		<plugin.provider>Dan Fornika</plugin.provider>
 		<plugin.dependencies></plugin.dependencies>
 		<plugin.requires.runtime>1.0.0</plugin.requires.runtime>

diff --git a/...blichealthbioinformatics/irida/plugin/resistancescreen/ResistanceScreenPluginUpdater.java b/...blichealthbioinformatics/irida/plugin/resistancescreen/ResistanceScreenPluginUpdater.java
@@ -96,11 +96,15 @@ public void update(Collection<Sample> samples, AnalysisSubmission analysis) thro
 			for (Map<String, String> geneDetectionStatus : geneDetectionStatuses) {
 				String geneName = geneDetectionStatus.get("gene_name");
 				String geneDetected = geneDetectionStatus.get("detected");
-				PipelineProvidedMetadataEntry geneDetectedEntry = new PipelineProvidedMetadataEntry(geneDetected, "boolean", analysis);
-
-				// key will be string like 'abricate-screen/KPC/detected'
-				String key = workflowName + "/" + geneName + "/" + "detected";
+				String alleles = geneDetectionStatus.get("alleles");
+				PipelineProvidedMetadataEntry geneDetectedEntry = new PipelineProvidedMetadataEntry(geneDetected, "xs:boolean", analysis);
+				PipelineProvidedMetadataEntry allelesEntry = new PipelineProvidedMetadataEntry(alleles, "xs:string", analysis);
+				// key will be string like 'resistance-screen/KPC/detected'
+				String key;
+				key = workflowName + "/" + geneName + "/" + "detected";
 				metadataEntries.put(key, geneDetectedEntry);
+				key = workflowName + "/" + geneName + "/" + "alleles";
+				metadataEntries.put(key, allelesEntry);
 			}
 
 			Map<MetadataTemplateField, MetadataEntry> metadataMap = metadataTemplateService.getMetadataMap(metadataEntries);
@@ -125,8 +129,8 @@ public void update(Collection<Sample> samples, AnalysisSubmission analysis) thro
 	 *                 the pipeline. This file should contain contents like:
 	 * 
 	 *                 <pre>
-	 * gene_name	detected
-	 * KPC	True
+	 * gene_name	detected	alleles
+	 * KPC	True	KPC-2
 	 * OXA	False
 	 *                 </pre>
 	 * 
@@ -147,7 +151,7 @@ List<Map<String, String>> parseGeneDetectionStatusFile(Path geneDetectionStatusF
 			HashMap<String, String> geneDetectionStatus = new HashMap<>();
 			String geneDetectionStatusLine;
 			while (( geneDetectionStatusLine = geneDetectionStatusReader.readLine()) != null) {
-				String[] geneDetectionStatusEntries = geneDetectionStatusLine.split("\t");
+				String[] geneDetectionStatusEntries = geneDetectionStatusLine.split("\t", -1);
 				for (int i = 0; i < fieldNames.length; i++) {
 					geneDetectionStatus.put(fieldNames[i], geneDetectionStatusEntries[i]);
 				}

diff --git a/src/main/resources/workflows/0.2.0/irida_workflow.xml b/src/main/resources/workflows/0.2.0/irida_workflow.xml
@@ -2,51 +2,36 @@
 <iridaWorkflow>
   <id>1f40bbf2-4080-4cf7-a846-988e602eaa30</id>
   <name>resistance-screen</name>
-  <version>0.1.1</version>
+  <version>0.2.0</version>
   <analysisType>RESISTANCE_SCREEN</analysisType>
   <inputs>
     <sequenceReadsPaired>sequence_reads_paired</sequenceReadsPaired>
     <requiresSingleSample>true</requiresSingleSample>
   </inputs>
   <parameters>
-    <parameter name="shovill-1-adv.nocorr" defaultValue="true">
-      <toolParameter toolId="toolshed.g2.bx.psu.edu/repos/iuc/shovill/shovill/1.0.4" parameterName="adv.nocorr" label="Disable post-assembly correction" type="boolean"/>
-    </parameter>
     <parameter name="shovill-1-adv.mincov" defaultValue="2">
       <toolParameter toolId="toolshed.g2.bx.psu.edu/repos/iuc/shovill/shovill/1.0.4" parameterName="adv.mincov" label="Minimum contig coverage" type="integer"/>
     </parameter>
-    <parameter name="shovill-1-trim" defaultValue="true">
-      <toolParameter toolId="toolshed.g2.bx.psu.edu/repos/iuc/shovill/shovill/1.0.4" parameterName="trim" label="Trim reads" type="boolean"/>
-    </parameter>
-    <parameter name="shovill-1-adv.namefmt" defaultValue="contig%05d">
-      <toolParameter toolId="toolshed.g2.bx.psu.edu/repos/iuc/shovill/shovill/1.0.4" parameterName="adv.namefmt" label="Contig name format" type="text"/>
-    </parameter>
-    <parameter name="shovill-1-adv.depth" defaultValue="100">
-      <toolParameter toolId="toolshed.g2.bx.psu.edu/repos/iuc/shovill/shovill/1.0.4" parameterName="adv.depth" label="Depth" type="integer"/>
-    </parameter>
     <parameter name="shovill-1-adv.gsize" defaultValue="">
       <toolParameter toolId="toolshed.g2.bx.psu.edu/repos/iuc/shovill/shovill/1.0.4" parameterName="adv.gsize" label="Estimated genome size" type="text"/>
     </parameter>
-    <parameter name="shovill-1-adv.opts" defaultValue="">
-      <toolParameter toolId="toolshed.g2.bx.psu.edu/repos/iuc/shovill/shovill/1.0.4" parameterName="adv.opts" label="Extra SPAdes options" type="text"/>
-    </parameter>
     <parameter name="shovill-1-adv.minlen" defaultValue="0">
       <toolParameter toolId="toolshed.g2.bx.psu.edu/repos/iuc/shovill/shovill/1.0.4" parameterName="adv.minlen" label="Minimum contig length" type="integer"/>
     </parameter>
-    <parameter name="shovill-1-assembler" defaultValue="spades">
-      <toolParameter toolId="toolshed.g2.bx.psu.edu/repos/iuc/shovill/shovill/1.0.4" parameterName="assembler" label="Assembler to use" type="select"/>
-    </parameter>
-    <parameter name="abricate-2-adv.db" defaultValue="card">
-      <toolParameter toolId="toolshed.g2.bx.psu.edu/repos/iuc/abricate/abricate/0.9.8" parameterName="adv.db"/>
-    </parameter>
     <parameter name="abricate-2-adv.min_dna_id" defaultValue="75.0">
       <toolParameter toolId="toolshed.g2.bx.psu.edu/repos/iuc/abricate/abricate/0.9.8" parameterName="adv.min_dna_id"/>
     </parameter>
-    <parameter name="screen_abricate_report-3-abricate_screening_file" required="true">
+    <parameter name="screen_abricate_report-4-abricate_screening_file" required="true">
       <dynamicSource>
           <galaxyToolDataTable name="abricate_report_screening_files" displayColumn="name" parameterColumn="value" />
       </dynamicSource>
-      <toolParameter toolId="toolshed.g2.bx.psu.edu/repos/public-health-bioinformatics/screen_abricate_report/screen_abricate_report/0.1.0" parameterName="screening_file"/>
+      <toolParameter toolId="toolshed.g2.bx.psu.edu/repos/public-health-bioinformatics/screen_abricate_report/screen_abricate_report/0.4.0+galaxy0" parameterName="screening_file_source.screening_file"/>
+    </parameter>
+    <parameter name="screen_abricate_report-4-min_coverage" defaultValue="90.0">
+      <toolParameter toolId="toolshed.g2.bx.psu.edu/repos/public_health_bioinformatics/screen_abricate_report/screen_abricate_report/0.4.0+galaxy0" parameterName="min_coverage"/>
+    </parameter>
+    <parameter name="screen_abricate_report-4-min_identity" defaultValue="90.0">
+      <toolParameter toolId="toolshed.g2.bx.psu.edu/repos/public_health_bioinformatics/screen_abricate_report/screen_abricate_report/0.4.0+galaxy0" parameterName="min_identity"/>
     </parameter>
   </parameters>
   <outputs>
@@ -55,6 +40,7 @@
     <output name="abricate_report_full" fileName="abricate_report_full.tsv"/>
     <output name="quast" fileName="quast.tsv"/>
     <output name="assembly" fileName="assembly.fasta"/>
+    <output name="abricate_report_screening_file" fileName="abricate_report_screening_file.tsv"/>
   </outputs>
   <toolRepositories>
     <repository>
@@ -79,7 +65,7 @@
       <name>screen_abricate_report</name>
       <owner>public-health-bioinformatics</owner>
       <url>https://toolshed.g2.bx.psu.edu</url>
-      <revision>b2d56a44a872</revision>
+      <revision>22247b1a59d5</revision>
     </repository>
     <repository>
       <name>data_manager_manual</name>